No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by agentrhq · MCP Server · ★ 92
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is authsome safe to install? View the security audit →
Credential broker and vault for AI Agents Docs · <a href="htt
| Stars | 92 |
| Forks | 10 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 72.0954070802853/100 |
| Open Issues | 11 |
| Last Updated | 2026-07-24 |
| Created | 2026-04-16 |
| Platforms | claude-code, cli, mcp, python |
| Est. Tokens | ~15k |
These tools work well together with authsome for enhanced workflows:
Looking for a authsome alternative? If you're comparing authsome with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor,
Supercharge AI Agents, Safely
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
Manage and orchestrate your Claude Code, Codex, Cursor, Antigravity, Kimi, Grok, Devin, Droid sessions on your
Local-first MCP password and credential manager for AI agents. Use passwords, API keys, SSH identities, and TO
Persistent Claude Code agents with scheduling, sessions, memory, and Telegram.
Explore other popular mcp server tools:
authsome is Credential gateway for AI agents. Log in once via Oauth2 or API Key. Every agent stays authenticated — headless, no SaaS, agents never see your credentials.. It is categorized as a MCP Server with 92 GitHub stars.
authsome is primarily written in Python. It covers topics such as agent-identity, agent-security, ai-agents.
You can find installation instructions and usage details in the authsome GitHub repository at github.com/agentrhq/authsome. The project has 92 stars and 10 forks, indicating an active community.
authsome is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to authsome on Agent Skills Hub include rampart, mcpproxy-go, maestro. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: